Deep Learning Based Automatic Grape Downy Mildew Detection

Zhao Zhang; Yongliang Qiao; Yangyang Guo; Dongjian He

doi:10.3389/fpls.2022.872107

Deep Learning Based Automatic Grape Downy Mildew Detection

Front Plant Sci. 2022 Jun 9:13:872107. doi: 10.3389/fpls.2022.872107. eCollection 2022.

Authors

Zhao Zhang^{1

2

3

4}, Yongliang Qiao⁵, Yangyang Guo^{1

3

4}, Dongjian He^{1

3

4}

Affiliations

¹ College of Mechanical and Electronic Engineering, Northwest A&F University, Xianyang, China.
² College of Electronic and Electrical Engineering, Baoji University of Arts and Sciences, Baoji, China.
³ Key Laboratory of Agricultural Internet of Things, Ministry of Agriculture and Rural Affairs, Northwest A&F University, Xianyang, China.
⁴ Shaanxi Key Laboratory of Agricultural Information Perception and Intelligent Service, Northwest A&F University, Xianyang, China.
⁵ Faculty of Engineering, Australian Centre for Field Robotics (ACFR), The University of Sydney, Sydney, NSW, Australia.

Abstract

Grape downy mildew (GDM) disease is a common plant leaf disease, and it causes serious damage to grape production, reducing yield and fruit quality. Traditional manual disease detection relies on farm experts and is often time-consuming. Computer vision technologies and artificial intelligence could provide automatic disease detection for real-time controlling the spread of disease on the grapevine in precision viticulture. To achieve the best trade-off between GDM detection accuracy and speed under natural environments, a deep learning based approach named YOLOv5-CA is proposed in this study. Here coordinate attention (CA) mechanism is integrated into YOLOv5, which highlights the downy mildew disease-related visual features to enhance the detection performance. A challenging GDM dataset was acquired in a vineyard under a nature scene (consisting of different illuminations, shadows, and backgrounds) to test the proposed approach. Experimental results show that the proposed YOLOv5-CA achieved a detection precision of 85.59%, a recall of 83.70%, and a mAP@0.5 of 89.55%, which is superior to the popular methods, including Faster R-CNN, YOLOv3, and YOLOv5. Furthermore, our proposed approach with inference occurring at 58.82 frames per second, could be deployed for the real-time disease control requirement. In addition, the proposed YOLOv5-CA based approach could effectively capture leaf disease related visual features resulting in higher GDE detection accuracy. Overall, this study provides a favorable deep learning based approach for the rapid and accurate diagnosis of grape leaf diseases in the field of automatic disease detection.

Keywords: attention mechanism; data augmentation; deep learning; digital agriculture; disease detection; grape downy mildew.